Please use this identifier to cite or link to this item:
Title: Distributed multi-task classification : a decentralized online learning approach
Authors: Zhang, Chi
Zhao, Peilin
Hao, Shuji
Soh, Yeng Chai
Lee, Bu Sung
Miao, Chunyan
Hoi, Steven C. H.
Keywords: Decentralized Distributed Learning
Multi-task Learning
Engineering::Electrical and electronic engineering
Issue Date: 2018
Source: Zhang, C., Zhao, P., Hao, S., Soh, Y. C., Lee, B. S., Miao, C., & Hoi, S. C. H. (2018). Distributed multi-task classification: a decentralized online learning approach. Machine Learning, 107(4), 727-747. doi:10.1007/s10994-017-5676-y
Series/Report no.: Machine Learning
Abstract: Although dispersing one single task to distributed learning nodes has been intensively studied by the previous research, multi-task learning on distributed networks is still an area that has not been fully exploited, especially under decentralized settings. The challenge lies in the fact that different tasks may have different optimal learning weights while communication through the distributed network forces all tasks to converge to an unique classifier. In this paper, we present a novel algorithm to overcome this challenge and enable learning multiple tasks simultaneously on a decentralized distributed network. Specifically, the learning framework can be separated into two phases: (i) multi-task information is shared within each node on the first phase; (ii) communication between nodes then leads the whole network to converge to a common minimizer. Theoretical analysis indicates that our algorithm achieves a O(T−−√) regret bound when compared with the best classifier in hindsight, which is further validated by experiments on both synthetic and real-world datasets.
ISSN: 0885-6125
DOI: 10.1007/s10994-017-5676-y
Schools: School of Computer Science and Engineering 
School of Electrical and Electronic Engineering 
Rights: © 2017 The Author(s). All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 20

Updated on Jun 7, 2024

Web of ScienceTM
Citations 20

Updated on Oct 20, 2023

Page view(s) 20

Updated on Jun 14, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.